Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 85 for “"Noisy Labels"”.
-
Differentially Private Learning with Noisy Labels
… datasets is a difficult task and often leads to noisy labels due to human errors or adversarial perturbation. Recent studies have shown multiple methods to tackle this problem in the non-private scenario, yet this remains an unsolved problem when the dataset is private. In this work, we aim to …
-
Learning from Noisy Labels using Robust Structures
… Crowdsourcing is a cost-effective way to gather labels, but it often fails to provide sufficient high-quality data. This raises a key question: How can we design robust structures to improve learning from noisy labels? Without such mechanisms, noisy labels from crowdsourced workers degrade model …
-
Robust Approaches for Learning with Noisy Labels
… obtaining large-scale datasets with correct labels is often expensive, time-consuming, and sometimes even impossible. Common approaches of constructing datasets involve some degree of error-prone processes, such as automatic labeling or crowdsourcing, which inherently introduce noisy labels. …
-
A GENERAL MODEL FOR NOISY LABELS IN MACHINE LEARNING
… models are simply reflections of the data and labels on which they are trained. To wit, if the data and labels are suspect, then so too must be the models that we rely on—yet, as larger and more comprehensive datasets become standard in contemporary machine learning, it becomes increasingly …
-
CREDIBILITY ASSESSMENT FOR ARABIC MICRO-BLOGS USING NOISY LABELS
… is proposed when deriving the credibility labels for the messages in the training and testing dataset. This credibility model primarily uses similarity and accuracy rating measurements for evaluating the weighting of labellers.<br/>In order to evaluate proposed model, we compare the …
-
Machine Learning Methods for Computational Phenotyping Using Patient Healthcare Data with Noisy Labels
Positive and Unlabeled (PU) learning problems abound in many real-world applications. In healthcare informatics, diagnosed patients are considered labeled positive for a specific disease, but being undiagnosed does not mean they can be labeled negative. PU learning can improve classification …
-
Multi-task learning for leveraging noisy labels in automatic analysis of ultrasound images
… is a tedious process, fine-grained and extensive labels are usually not available. The size of data is often limited, and missing labels are an issue. Due to observer variability among different annotators, there is variability in ground truth that manifests as a type of label noise. This thesis …
-
Identifying Noisy Labels in the Ground Truth of Eating Episodes Self-Reported by Button Press on a Wrist-worn Device
This thesis considers the problem of identifying noisy labels in the ground truth of eating episodes (meals, snacks) as self-reported by participants collecting data in the wild. Participants wore a smartwatch-like device that tracked their wrist motion all day. They were instructed to press a …
-
Instance-Aware Learning in the Presence of Label Noise: An Adaptive Framework for Image Classification
… datasets. Such quality is negatively affected by noisy labels, which can significantly degrade the training process of the models and reduce their accuracy and generalisation capabilities. Traditionally, noisy labels have been viewed as random labelling mistakes, in which the resulting noisy label …
-
Evaluating Information Retrieval Systems With Multiple Non-Expert Assessors
… judging abilities, and the aggregation of the noisy labels into one single consensus label. Much previous work has shown how to utilize this method to replace expert labels in the relevance evaluation. However, the effects of relevance judgment errors on the ranking system evaluation have been …
-
Towards the Safety and Robustness of Deep Models
… Backdoor Attack, ii) Backdoor Defense, and iii) Noisy Labels. First, we study the backdoor attack creation and detection from different perspectives. Backdoor attack addresses AI safety and robustness issues where an adversary can insert malicious behavior into a DNN by altering the training …
-
Techniques to Improve Classification Performance for Biomedical Applications with Limited Training Data and Variability
… may be available. Transferring record labels to cycles may lead to noisy labels. Learning to classify with limited data with variability due to heterogeneity and noisy labels is a hard problem, and this dissertation provides novel techniques for learning under such scenarios. Techniques …
-
Towards Robust Deep Learning for Medical Imaging with Limited and Noisy Labeled Data
… variability. Models trained on limited or noisy labeled data suffer from poor performance due to overfitting, thus reducing their generalizability and trustworthiness for medical applications. During recent years, several works have been proposed to tackle the challenge of learning with …
-
Annotation-Free Deep Learning of Large-Scale Nuclear Segmentation and Spatial Neighborhood Analysis on Multiplexed Fluorescence Images
… driving pipeline for Brain Cell Analysis using noisy Labels with minimal human input. 1) It uses a parametric method to generate noisy labels for cell nuclei and refines through an iterative training process. 2) We introduce a background recovery technique to enhance the detection and estimation …
-
Towards a Reliable Deep Learning Framework for Prostate Cancer Diagnosis using Ultrasound
… (DL) models for PCa detection is hindered by noisy labels and cancer heterogeneity. The purpose of this work is to develop a clinically applicable framework for DL-based detection of PCa from ultrasound that is robust to noise and uncertainty inherent to ultrasound images and their associated …
-
Enhancing Model Generalization in Weakly Supervised and Low-Shot Transfer Learning Scenarios
… the amount of data, such as weakly supervised labels or transfer learning from other domains. In this thesis, we explore two methods drawn from these areas for reducing the number of labels required to train DNNs. Weakly supervised labels can be mined from sources such as the internet. These …
-
Semisupervised sentiment analysis of tweets based on noisy emoticon labels
… and ':(') to collect a large training set with noisy labels using little human intervention and trains a Maximum Entropy classifier on that training set. Results on two hand-labeled test corpora are compared to various baselines and a keyword-based heuristic approach, with the machine learned …
-
Integrating Multiple Deep Learning Models for Disaster Description in Low-Altitude Videos
… low-altitude imagery with highly imbalanced and noisy labels. We utilize labeled images from the LADI dataset to formulate a solution for general problem in disaster classification and object detection. Our research integrated and developed multiple deep learning models that does the object …
-
AUTOMATED SURFACE INSPECTION FOR INDUSTRIAL APPLICATIONS
… classification, multiclass ASI, and weak and noisy labels are proposed. The second part focuses on global abnormalities, where a method using region-based graph is proposed for titanium alloy inspection. The experimental results on multiple public and industrial datasets show that the proposed …
-
Understanding and Enriching the Algorithmic Reasoning Capabilities of Deep Learning Models
… to out-of-distribution data, learn under noisy labels, and make better sequential decisions --- all of these require the models to have varying levels of reasoning capabilities. As the reasoning process can be described as a step-by-step algorithmic procedure, understanding and enriching …
Page 1 of 5